Cleanups & readme

* Move line-item transformations to own package
* Have WordFormat names instead of whole enum in globals
* Rename PdfUploadView to UploadView
* Correct license

README.md

@@ -0,0 +1,32 @@
+# PDF-To-Markdown Converter
+
+Javascript tool to parse PDF files and convert them into Markdwon format. Online version at http://pdf2md.morethan.io!
+
+## Major Changes
+
+- **Apr 2017** - 0.1: Initial Release
+
+## Contribute
+
+Use the [issue tracker](https://github.com/jzillmann/pdf-to-markdown/issues) and/or open [pull requests](https://github.com/jzillmann/pdf-to-markdown/pulls)!
+
+#### Useful Build Commands
+
+- ```npm install``` Download all necessary npm packages
+- ```npm run lint``` Lint the javascript files
+- ```npm run test``` Run tests
+- ```npm run check``` Lint $ Test
+- ```npm run watch``` Continuously build the project
+- ```open build/index.html``` Open the build project in your default browser
+- ```npm run release``` Build production version
+- ```npm run deploy``` Build production version & move it to the github pages fodler
+
+#### Release
+- Increase version in package.json
+- ```npm run deploy```
+- commit & push
+
+
+## Credits
+
+[pdf.js](https://mozilla.github.io/pdf.js/) - Mozilla's PDF parsing & rendering platform which is used as a raw parser

package.json

@@ -8,6 +8,7 @@
     "build": "webpack",
     "lint": "eslint src --ext .js --ext .jsx --cache",
     "test": "mocha --compilers js:babel-core/register test --recursive",
+    "check": "npm run lint && npm run test",
     "release": "npm run lint && rm -rf build/* && NODE_ENV=production webpack -p",
     "deploy": "npm run release && cp -r build/* docs/"
   },
@@ -17,7 +18,7 @@
     "Converter"
   ],
   "author": "Johannes Zillmann",
-  "license": "Apache-2.0",
+  "license": "AGPL-3.0",
   "repository": {
     "type": "git",
     "url": "https://github.com/jzillmann/pdf-to-markdown"

src/javascript/components/App.jsx

@@ -5,7 +5,7 @@ import Grid from 'react-bootstrap/lib/Grid'
 import TopBar from './TopBar.jsx';
 import FooterBar from './FooterBar.jsx'
 import { View } from '../models/AppState.jsx';
-import PdfUploadView from './PdfUploadView.jsx';
+import UploadView from './UploadView.jsx';
 import LoadingView from './LoadingView.jsx';
 import ResultView from './ResultView.jsx';
 import DebugView from './DebugView.jsx';
@@ -23,7 +23,7 @@ export default class App extends React.Component {
         var mainView;
         switch (this.props.appState.mainView) {
         case View.UPLOAD:
-            mainView = <PdfUploadView uploadPdfFunction={ appState.storeFileBuffer } />
+            mainView = <UploadView uploadPdfFunction={ appState.storeFileBuffer } />
             break;
         case View.LOADING:
             mainView = <LoadingView fileBuffer={ appState.fileBuffer } storePdfPagesFunction={ appState.storePdfPages } />

src/javascript/components/DebugView.jsx

@@ -116,37 +116,36 @@ export default class DebugView extends React.Component {
 
         return (
             <div>
-              <AutoAffix viewportOffsetTop={ 15 } container={ this }>
+              <AutoAffix viewportOffsetTop={ 0 } offsetTop={ 0 } container={ this }>
                 <table>
                   <tbody>
-                    { lastTransformation.showPageSelection() &&
+                    <tr>
-                      <tr>
+                      <td>
-                        <td>
+                        <div>
-                          <div>
+                          <ul className='pagination'>
-                            <ul className='pagination'>
+                            <li className={ pageNr == -1 ? 'active' : '' }>
-                              <li className={ pageNr == -1 ? 'active' : '' }>
+                              <a role='button' onClick={ this.selectPage.bind(this, 0) }>ALL</a>
-                                <a role='button' onClick={ this.selectPage.bind(this, 0) }>ALL</a>
+                            </li>
-                              </li>
+                          </ul>
-                            </ul>
+                          <Pagination
-                            <Pagination
+                                      prev
-                                        prev
+                                      next
-                                        next
+                                      first
-                                        first
+                                      last
-                                        last
+                                      ellipsis
-                                        ellipsis
+                                      boundaryLinks
-                                        boundaryLinks
+                                      items={ pages.length }
-                                        items={ pages.length }
+                                      maxButtons={ 17 }
-                                        maxButtons={ 17 }
+                                      activePage={ this.state.pageNr + 1 }
-                                        activePage={ this.state.pageNr + 1 }
+                                      onSelect={ this.selectPage.bind(this) } />
-                                        onSelect={ this.selectPage.bind(this) } />
+                        </div>
-                          </div>
+                      </td>
-                        </td>
+                      <td style={ { padding: '5px', textAlign: 'left' } }>
-                        <td style={ { padding: '5px', textAlign: 'left' } }>
+                        <Label bsStyle="info">
-                          <Label bsStyle="info">
+                          Pages
-                            Pages
+                        </Label>
-                          </Label>
+                      </td>
-                        </td>
+                    </tr>
-                      </tr> }
                     <tr>
                       <td>
                         <ButtonToolbar>

src/javascript/components/UploadView.jsx

@@ -5,7 +5,7 @@ import Alert from 'react-bootstrap/lib/Alert'
 import Dropzone from 'react-dropzone'
 import FaCloudUpload from 'react-icons/lib/fa/cloud-upload'
 
-export default class PdfUploadView extends React.Component {
+export default class UploadView extends React.Component {
 
     static propTypes = {
         uploadPdfFunction: React.PropTypes.func.isRequired,
@@ -42,7 +42,7 @@ export default class PdfUploadView extends React.Component {
                 <h1><FaCloudUpload width={ 100 } height={ 100 } /></h1>
                 <br/>
                 <Alert bsStyle="warning">
-                  <i>This tool converts a PDF file into a Markdown text format! Simply drag & drop your PDF file on the upload area and go from there. Don't expect wonders, there are a lot of variances in generated PDF's from different tools and different ages. Though this tool aims to be general purpose, it has been tested on a certain set of PDF's only.</i>
+                  <i>This tool converts a PDF file into a Markdown text format! Simply drag & drop your PDF file on the upload area and go from there. Don't expect wonders, there are a lot of variances in generated PDF's from different tools and different ages. No matter how good the parser works for your PDF, you will have to invest a good amount of manuell work to complete it. Though this tool aims to be general purpose, it has been tested on a certain set of PDF's only.</i>
                 </Alert>
               </Dropzone>
               <br/>

src/javascript/models/AppState.jsx

@@ -2,12 +2,12 @@ import { Enum } from 'enumify';
 
 import CalculateGlobalStats from './transformations/textitem/CalculateGlobalStats.jsx';
 
-import CompactLines from './transformations/textitem/CompactLines.jsx';
+import CompactLines from './transformations/lineitem/CompactLines.jsx';
-import RemoveRepetitiveElements from './transformations/textitem/RemoveRepetitiveElements.jsx'
+import RemoveRepetitiveElements from './transformations/lineitem/RemoveRepetitiveElements.jsx'
-import VerticalToHorizontal from './transformations/textitem/VerticalToHorizontal.jsx';
+import VerticalToHorizontal from './transformations/lineitem/VerticalToHorizontal.jsx';
-import DetectTOC from './transformations/textitem/DetectTOC.jsx'
+import DetectTOC from './transformations/lineitem/DetectTOC.jsx'
-import DetectListItems from './transformations/textitem/DetectListItems.jsx'
+import DetectListItems from './transformations/lineitem/DetectListItems.jsx'
-import DetectHeaders from './transformations/textitem/DetectHeaders.jsx'
+import DetectHeaders from './transformations/lineitem/DetectHeaders.jsx'
 
 import GatherBlocks from './transformations/textitemblock/GatherBlocks.jsx'
 import DetectCodeQuoteBlocks from './transformations/textitemblock/DetectCodeQuoteBlocks.jsx'

src/javascript/models/LineConverter.jsx

@@ -1,6 +1,7 @@
 import TextItem from './TextItem.jsx';
 import Word from './Word.jsx';
 import WordType from './markdown/WordType.jsx';
+import WordFormat from './markdown/WordFormat.jsx';
 import LineItem from './LineItem.jsx';
 import StashingStream from './StashingStream.jsx';
 import { ParsedElements } from './PageItem.jsx';
@@ -115,9 +116,10 @@ class WordDetectionStream extends StashingStream {
         results.push(...this.itemsToWords(stash, format));
     }
 
-    itemsToWords(items, format) {
+    itemsToWords(items, formatName) {
         const combinedText = combineText(items);
         const words = combinedText.split(' ');
+        const format = formatName ? WordFormat.enumValueOf(formatName) : null;
         return words.filter(w => w.trim().length > 0).map(word => {
             var type = null;
             if (word.startsWith('http:')) {

src/javascript/models/transformations/ToLineItemBlockTransformation.jsx

@@ -16,10 +16,6 @@ export default class ToLineItemBlockTransformation extends Transformation {
         this.showWhitespaces = false;
     }
 
-    showPageSelection() {
-        return true;
-    }
-
     showModificationCheckbox() {
         return true;
     }

src/javascript/models/transformations/ToLineItemTransformation.jsx

@@ -16,10 +16,6 @@ export default class ToLineItemTransformation extends Transformation {
         this.showWhitespaces = false;
     }
 
-    showPageSelection() {
-        return true;
-    }
-
     showModificationCheckbox() {
         return true;
     }

src/javascript/models/transformations/ToTextItemTransformation.jsx

@@ -16,10 +16,6 @@ export default class ToTextItemTransformation extends Transformation {
         this.showWhitespaces = false;
     }
 
-    showPageSelection() {
-        return true;
-    }
-
     showModificationCheckbox() {
         return true;
     }

src/javascript/models/transformations/Transformation.jsx

@@ -14,10 +14,6 @@ export default class Transformation {
         this.itemType = itemType;
     }
 
-    showPageSelection() {
-        return true;
-    }
-
     showModificationCheckbox() {
         return false;
     }

src/javascript/models/transformations/textitem/CalculateGlobalStats.jsx

@@ -67,7 +67,7 @@ export default class CalculateGlobalStats extends ToTextItemTransformation {
                 format = WordFormat.BOLD;
             }
             if (format) {
-                fontToFormats.set(key, format);
+                fontToFormats.set(key, format.name);
             }
         });
         fontIdToName.sort();